# -*- coding: utf-8 -*-
"""1040_249_949

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1T8VCDZs5tRg-mTI4qNqCct_92fcd_7Rl
"""

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
import warnings as w
w.filterwarnings('ignore')

df=pd.read_csv('//content/1000_ml_jobs_us.csv')

df.head()

df.isnull().sum()

df.drop(columns=['company_website', 'company_description', 'job_description_text', 'Unnamed: 0'], inplace=True)

df['company_address_locality'] = df['company_address_locality'].fillna(df['company_address_locality'].mode()[0])
df['company_address_region'] = df['company_address_region'].fillna(df['company_address_region'].mode()[0])
df['seniority_level'] = (df['seniority_level'].fillna(df['seniority_level']).mode()[0])

df.info()

df['job_posted_date'] = pd.to_datetime(df['job_posted_date'])

df['company_address_locality'].value_counts().head(10).plot(kind='bar', title='Top 10 Localities')

df['company_address_region'].value_counts().head(10).plot(kind='bar', title='Top 10 Regions')

df['company_name'].value_counts().head(10).plot(kind='barh', title='Top 10 Hiring Companies')

df['seniority_level'].value_counts().plot(kind='pie', autopct='%1.1f%%', title='Seniority Level Distribution')

df['job_title'].value_counts().head(15).plot(kind='bar', title='Top 15 Job Titles')

import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, accuracy_score
import warnings as w
w.filterwarnings('ignore')

# Load data (assuming the previous steps for loading and cleaning the data were successful)
# df=pd.read_csv('//content/1000_ml_jobs_us.csv')
# ... (previous data cleaning and preparation steps) ...

le = LabelEncoder()

# Apply LabelEncoder to all relevant categorical columns outside the training loop
for col in ['job_posted_date', 'company_address_locality', 'company_address_region', 'company_name', 'job_title']:
  df[col] = le.fit_transform(df[col].astype(str))

# Define features (X) and target (y) after encoding
X = df.drop('seniority_level', axis=1)
y = le.fit_transform(df['seniority_level']) # Encode the target variable as well

# Perform the train-test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Initialize and train the model
model = RandomForestClassifier(random_state=42)
model.fit(X_train, y_train)

# Make predictions and evaluate the model
y_pred = model.predict(X_test)

print("Accuracy:", accuracy_score(y_test, y_pred))
print(classification_report(y_test, y_pred))